# Refocusing on Relevance: Personalization in NLG

arXiv: https://arxiv.org/abs/2109.05140 · HTML: https://mlsanity.com/paper/2109.05140/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 81 references that are in the map.
- First posted on arXiv 10 Sep 2021.

## Builds on (most cited first, 22 of 22)

- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018)
- [Towards a Human-like Open-Domain Chatbot](https://mlsanity.com/paper/2001.09977/) (2020)
- [Newsroom: A Dataset of 1.3 Million Summaries with Diverse Extractive Strategies](https://mlsanity.com/paper/1804.11283/) (2018)
- [Deep Reinforcement Learning for Dialogue Generation](https://mlsanity.com/paper/1606.01541/) (2016)
- [Why We Need New Evaluation Metrics for NLG](https://mlsanity.com/paper/1707.06875/) (2017)
- [A Persona-Based Neural Conversation Model](https://mlsanity.com/paper/1603.06155/) (2016)
- [Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview](https://mlsanity.com/paper/1912.11078/) (2019)
- [TLDR: Extreme Summarization of Scientific Documents](https://mlsanity.com/paper/2004.15011/) (2020)
- [Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems](https://mlsanity.com/paper/1508.01745/) (2015)
- [Assessing Gender Bias in Machine Translation -- A Case Study with Google Translate](https://mlsanity.com/paper/1809.02208/) (2018)
- [A Distributional Approach to Controlled Text Generation](https://mlsanity.com/paper/2012.11635/) (2020)
- [MoEL: Mixture of Empathetic Listeners](https://mlsanity.com/paper/1908.07687/) (2019)
- [Personalizing Dialogue Agents via Meta-Learning](https://mlsanity.com/paper/1905.10033/) (2019)
- [Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling](https://mlsanity.com/paper/2107.03451/) (2021)
- [Towards Persona-Based Empathetic Conversational Models](https://mlsanity.com/paper/2004.12316/) (2020)
- [Paraphrasing with Large Language Models](https://mlsanity.com/paper/1911.09661/) (2019)
- [Are Some Words Worth More than Others?](https://mlsanity.com/paper/2010.06069/) (2020)
- [Communication-based Evaluation for Natural Language Generation](https://mlsanity.com/paper/1909.07290/) (2019)

## Built on by (most cited first, 18 of 18)

- [LaMP: When Large Language Models Meet Personalization](https://mlsanity.com/paper/2304.11406/) (2023)
- [Learning Personalized Alignment for Evaluating Open-ended Text Generation](https://mlsanity.com/paper/2310.03304/) (2023)
- [RECAP: Retrieval-Enhanced Context-Aware Prefix Encoder for Personalized Dialogue Response Generation](https://mlsanity.com/paper/2306.07206/) (2023)
- [The AI Ghostwriter Effect: When Users Do Not Perceive Ownership of AI-Generated Text But Self-Declare as Authors](https://mlsanity.com/paper/2303.03283/) (2023)
- [Editable User Profiles for Controllable Text Recommendation](https://mlsanity.com/paper/2304.04250/) (2023)
- [DecipherPref: Analyzing Influential Factors in Human Preference Judgments via GPT-4](https://mlsanity.com/paper/2305.14702/) (2023)
- [PRODIGy: a PROfile-based DIalogue Generation dataset](https://mlsanity.com/paper/2311.05195/) (2023)
- [Social Skill Training with Large Language Models](https://mlsanity.com/paper/2404.04204/) (2024)
- ["One-Size-Fits-All"? Examining Expectations around What Constitute "Fair" or "Good" NLG System Behaviors](https://mlsanity.com/paper/2310.15398/) (2023)
- [Steering AI-Driven Personalization of Scientific Text for General Audiences](https://mlsanity.com/paper/2411.09969/) (2024)
- [Benchmarking and Improving LLM Robustness for Personalized Generation](https://mlsanity.com/paper/2509.19358/) (2025)
- [Reference-less Analysis of Context Specificity in Translation with Personalised Language Models](https://mlsanity.com/paper/2303.16618/) (2023)
- [MCPDial: A Minecraft Persona-driven Dialogue Dataset](https://mlsanity.com/paper/2410.21627/) (2024)
- [A Survey on Conversational Search and Applications in Biomedicine](https://mlsanity.com/paper/2211.15328/) (2022)
- [A Major Obstacle for NLP Research: Let's Talk about Time Allocation!](https://mlsanity.com/paper/2211.16858/) (2022)
- [FedPC: Federated Learning for Language Generation with Personal and Context Preference Embeddings](https://mlsanity.com/paper/2210.03766/) (2022)
- [Personalized Chain-of-Thought Summarization of Financial News for Investor Decision Support](https://mlsanity.com/paper/2511.05508/) (2025)
- [Retrieval, not hallucinations, will be the limiting factor for LLM-based clinical AI tools](https://mlsanity.com/paper/2607.24793/) (2026)

## Abstract (arXiv)

Many NLG tasks such as summarization, dialogue response, or open domain question answering focus primarily on a source text in order to generate a target response. This standard approach falls short, however, when a user's intent or context of work is not easily recoverable based solely on that source text -- a scenario that we argue is more of the rule than the exception. In this work, we argue that NLG systems in general should place a much higher level of emphasis on making use of additional context, and suggest that relevance (as used in Information Retrieval) be thought of as a crucial tool for designing user-oriented text-generating tasks. We further discuss possible harms and hazards around such personalization, and argue that value-sensitive design represents a crucial path forward through these challenges.